write some doc

cacing69 · Sep 5, 2023 · 5839a73 · 5839a73
1 parent 304d7b1
commit 5839a73
Show file tree

Hide file tree

Showing 9 changed files with 54 additions and 113 deletions.
diff --git a/.gitignore b/.gitignore
@@ -4,6 +4,6 @@
 composer.lock
 run-cache.php
 .phpunit.result.cache
-.php-cs.fixer.cache
+.php-cs-fixer.cache
 phpunit.xml
 .note.md
diff --git a/.php-cs-fixer.cache b/.php-cs-fixer.cache
diff --git a/README.md b/README.md
@@ -105,7 +105,7 @@ For example, you have a simple HTML element as shown below.
 
 </details>
 
-### List function available
+### List definer available
 
 Below are the functions you are can use, they may change over time. <br>**Note:** nested function has been supported.
 | function | example | description |

diff --git a/composer.json b/composer.json
@@ -36,7 +36,8 @@
     "symfony/http-client": "^5.4|^6.3",
     "symfony/deprecation-contracts": "^2.5|^3.4",
     "symfony/dom-crawler": "5.4|^6.3",
-    "doctrine/collections": "^1.8|^2.1|^3.0"
+    "doctrine/collections": "^1.8|^2.1|^3.0",
+    "cocur/slugify": "dev-main"
   },
   "require-dev": {
     "phpunit/phpunit": "^8.0|^9.0|^10.0",

diff --git a/src/Cquery.php b/src/Cquery.php
@@ -33,13 +33,20 @@ class Cquery
      */
     private $loader;
 
+    /**
+    * A variable used to store the results of a query
+    *
+    * @var \Doctrine\Common\Collections\ArrayCollection
+    *
+    * The default results is null
+    */
     private $results;
 
     /**
      * Create a new Cquery instance.
      *
-     * @param \DOMNodeList|\DOMNode|string|null $source A source to use as the the source data, u can put html
-     * content/url page to scrape default is null
+     * @param \DOMNodeList|\DOMNode|string|null $source A source to use as the the source data
+     * u can put html content/url page to scrape default is null
      *
      * @param string $contentType Type of Data Content to be Used as Data Source default is 'html'
      */
@@ -58,32 +65,32 @@ public function __construct(string $source = null, $contentType = "html")
     }
 
     /**
-     * Adds a definer to the current source.
-     *
+     * Adds a source based on data given.
      * This method is used to determine the HTML element selector
      * that will serve as a property in each array element.
      *
-     * @param \Cacing69\Cquery\Definer|string $picks a selector to grab on element
+     * @param string $value set a source element selector to activate query
      * @return \Cacing69\Cquery\Cquery
-     * @throws \Cacing69\Cquery\CqueryException when the provided parameter is incorrect."
      */
-    public function define(...$defines): Cquery
+    public function from(string $value)
     {
-        $this->loader->define(...$defines);
+        $this->loader->from($value);
         return $this;
     }
 
     /**
-     * Adds a source based on data given.
+     * Adds a definer to the current source.
+     *
      * This method is used to determine the HTML element selector
      * that will serve as a property in each array element.
      *
-     * @param string $value set a source element selector to activate query
+     * @param \Cacing69\Cquery\Definer|string $picks a selector to grab on element
      * @return \Cacing69\Cquery\Cquery
+     * @throws \Cacing69\Cquery\CqueryException when the provided parameter is incorrect."
      */
-    public function from(string $value)
+    public function define(...$defines): Cquery
     {
-        $this->loader->from($value);
+        $this->loader->define(...$defines);
         return $this;
     }
 
@@ -102,7 +109,7 @@ public function limit(int $limit)
     }
 
     /**
-     * Take a first reesult from result collection
+     * Take a first result from result collection
      *
      * @return array
      */
@@ -147,7 +154,7 @@ public function orFilter($node, $operator = null, $value = null): Cquery
     }
 
     /**
-    * Take a result from query
+    * Take a result query from loader
     *
     * @return ArrayCollection
     */
@@ -188,38 +195,7 @@ public function getSource()
 
     public function client($clientType)
     {
-        // $this->loader->setClientType($clientType);
-
+        $this->loader->setClientType($clientType);
         return $this;
     }
-
-    public static function getAsync($results, $chunk)
-    {
-        $loop = Loop::get();
-        $client = new Browser($loop);
-        $results = array_chunk($results, 25);
-
-        foreach ($results as $key => $_chunks) {
-            foreach ($_chunks as $_key => $_result) {
-                $client
-                // ->withHeader("Key", "value")
-                // ->withHeader("Key", "value")
-                ->get($_result["url"])
-                ->then(function (ResponseInterface $response) use (&$results, $key, $_key) {
-                    $detail = new Cquery((string) $response->getBody());
-
-                    $resultDetail = $detail
-                        ->from(".spec")
-                        ->define(
-                            ".specleft tr:nth-child(1) > td.data as price"
-                        )
-                        ->first();
-                    $results[$key][$_key]["price"] = $resultDetail["price"];
-                });
-            }
-            $loop->run();
-        }
-
-        return array_merge(...$results);
-    }
 }
diff --git a/src/Loader.php b/src/Loader.php
@@ -16,8 +16,8 @@ abstract class Loader
 {
     use HasSourceProperty;
     protected $limit = null;
-    protected $clientType = "browser-kit";
     protected $client;
+    protected $clientType = "browser-kit";
 
     protected $uri = null;
     protected $isRemote = false;
@@ -238,6 +238,12 @@ public function setCallbackCompose(Closure $closure)
         return $this;
     }
 
+    public function setClientType(string $clientType)
+    {
+        $this->clientType = $clientType;
+        return $this;
+    }
+
     public function getResults()
     {
         return $this->results;

diff --git a/src/RegisterAdapter.php b/src/RegisterAdapter.php
@@ -11,6 +11,14 @@
 use Cacing69\Cquery\Adapter\ReverseCallbackAdapter;
 use Cacing69\Cquery\Adapter\UpperCallbackAdapter;
 
+/**
+ * RegisterAdapter used to register available adapters, this adapter is utilized during create definer and filter.
+ *
+ * @author Ibnul Mutaki <[email protected]>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
 class RegisterAdapter
 {
     public static function load()

diff --git a/src/Source.php b/src/Source.php
@@ -9,6 +9,14 @@
 use Cacing69\Cquery\Trait\HasRawProperty;
 use Symfony\Component\CssSelector\CssSelectorConverter;
 
+/**
+ * Source class used to define the source element to be scraped
+ *
+ * @author Ibnul Mutaki <[email protected]>
+ *
+ * For the full copyright and license information, please view the LICENSE
+ * file that was distributed with this source code.
+ */
 class Source
 {
     use HasAliasProperty;

diff --git a/src/Support/Str.php b/src/Support/Str.php
@@ -2,72 +2,15 @@
 
 namespace Cacing69\Cquery\Support;
 
+use Cocur\Slugify\Slugify;
+
 class Str
 {
-    // https://stackoverflow.com/a/2955521/10232729
-    public static function slug($text, $divider = "_"): string
+    public static function slug($text): string
     {
-        $replace = [
-            '<' => '', '>' => '', '-' => ' ', '&' => '', '.' => '',
-            '"' => '', 'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A',
-            'Ä' => 'A', 'Å' => 'A', 'Ā' => 'A', 'Ą' => 'A', 'Ă' => 'A', 'Æ' => 'Ae',
-            'Ç' => 'C', 'Ć' => 'C', 'Č' => 'C', 'Ĉ' => 'C', 'Ċ' => 'C', 'Ď' => 'D', 'Đ' => 'D',
-            'Ð' => 'D', 'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ē' => 'E',
-            'Ę' => 'E', 'Ě' => 'E', 'Ĕ' => 'E', 'Ė' => 'E', 'Ĝ' => 'G', 'Ğ' => 'G',
-            'Ġ' => 'G', 'Ģ' => 'G', 'Ĥ' => 'H', 'Ħ' => 'H', 'Ì' => 'I', 'Í' => 'I',
-            'Î' => 'I', 'Ï' => 'I', 'Ī' => 'I', 'Ĩ' => 'I', 'Ĭ' => 'I', 'Į' => 'I',
-            'İ' => 'I', 'Ĳ' => 'IJ', 'Ĵ' => 'J', 'Ķ' => 'K', 'Ł' => 'K', 'Ľ' => 'K',
-            'Ĺ' => 'K', 'Ļ' => 'K', 'Ŀ' => 'K', 'Ñ' => 'N', 'Ń' => 'N', 'Ň' => 'N',
-            'Ņ' => 'N', 'Ŋ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O',
-            'Ö' => 'Oe', 'Ø' => 'O', 'Ō' => 'O', 'Ő' => 'O', 'Ŏ' => 'O',
-            'Œ' => 'OE', 'Ŕ' => 'R', 'Ř' => 'R', 'Ŗ' => 'R', 'Ś' => 'S', 'Š' => 'S',
-            'Ş' => 'S', 'Ŝ' => 'S', 'Ș' => 'S', 'Ť' => 'T', 'Ţ' => 'T', 'Ŧ' => 'T',
-            'Ț' => 'T', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'Ue', 'Ū' => 'U',
-            'Ů' => 'U', 'Ű' => 'U', 'Ŭ' => 'U', 'Ũ' => 'U', 'Ų' => 'U',
-            'Ŵ' => 'W', 'Ý' => 'Y', 'Ŷ' => 'Y', 'Ÿ' => 'Y', 'Ź' => 'Z', 'Ž' => 'Z',
-            'Ż' => 'Z', 'Þ' => 'T', 'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a',
-            'ä' => 'ae', 'å' => 'a', 'ā' => 'a', 'ą' => 'a', 'ă' => 'a',
-            'æ' => 'ae', 'ç' => 'c', 'ć' => 'c', 'č' => 'c', 'ĉ' => 'c', 'ċ' => 'c',
-            'ď' => 'd', 'đ' => 'd', 'ð' => 'd', 'è' => 'e', 'é' => 'e', 'ê' => 'e',
-            'ë' => 'e', 'ē' => 'e', 'ę' => 'e', 'ě' => 'e', 'ĕ' => 'e', 'ė' => 'e',
-            'ƒ' => 'f', 'ĝ' => 'g', 'ğ' => 'g', 'ġ' => 'g', 'ģ' => 'g', 'ĥ' => 'h',
-            'ħ' => 'h', 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i', 'ī' => 'i',
-            'ĩ' => 'i', 'ĭ' => 'i', 'į' => 'i', 'ı' => 'i', 'ĳ' => 'ij', 'ĵ' => 'j',
-            'ķ' => 'k', 'ĸ' => 'k', 'ł' => 'l', 'ľ' => 'l', 'ĺ' => 'l', 'ļ' => 'l',
-            'ŀ' => 'l', 'ñ' => 'n', 'ń' => 'n', 'ň' => 'n', 'ņ' => 'n', 'ŉ' => 'n',
-            'ŋ' => 'n', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'oe',
-            'ø' => 'o', 'ō' => 'o', 'ő' => 'o', 'ŏ' => 'o', 'œ' => 'oe',
-            'ŕ' => 'r', 'ř' => 'r', 'ŗ' => 'r', 'š' => 's', 'ù' => 'u', 'ú' => 'u',
-            'û' => 'u', 'ū' => 'u', 'ü' => 'ue', 'ů' => 'u', 'ű' => 'u',
-            'ŭ' => 'u', 'ũ' => 'u', 'ų' => 'u', 'ŵ' => 'w', 'ý' => 'y', 'ÿ' => 'y',
-            'ŷ' => 'y', 'ž' => 'z', 'ż' => 'z', 'ź' => 'z', 'þ' => 't', 'ß' => 'ss',
-            'ſ' => 'ss', 'ый' => 'iy', 'А' => 'A', 'Б' => 'B', 'В' => 'V', 'Г' => 'G',
-            'Д' => 'D', 'Е' => 'E', 'Ё' => 'YO', 'Ж' => 'ZH', 'З' => 'Z', 'И' => 'I',
-            'Й' => 'Y', 'К' => 'K', 'Л' => 'L', 'М' => 'M', 'Н' => 'N', 'О' => 'O',
-            'П' => 'P', 'Р' => 'R', 'С' => 'S', 'Т' => 'T', 'У' => 'U', 'Ф' => 'F',
-            'Х' => 'H', 'Ц' => 'C', 'Ч' => 'CH', 'Ш' => 'SH', 'Щ' => 'SCH', 'Ъ' => '',
-            'Ы' => 'Y', 'Ь' => '', 'Э' => 'E', 'Ю' => 'YU', 'Я' => 'YA', 'а' => 'a',
-            'б' => 'b', 'в' => 'v', 'г' => 'g', 'д' => 'd', 'е' => 'e', 'ё' => 'yo',
-            'ж' => 'zh', 'з' => 'z', 'и' => 'i', 'й' => 'y', 'к' => 'k', 'л' => 'l',
-            'м' => 'm', 'н' => 'n', 'о' => 'o', 'п' => 'p', 'р' => 'r', 'с' => 's',
-            'т' => 't', 'у' => 'u', 'ф' => 'f', 'х' => 'h', 'ц' => 'c', 'ч' => 'ch',
-            'ш' => 'sh', 'щ' => 'sch', 'ъ' => '', 'ы' => 'y', 'ь' => '', 'э' => 'e',
-            'ю' => 'yu', 'я' => 'ya'
-        ];
-
-        // make a human readable string
-        $text = strtr($text, $replace);
-
-        // replace non letter or digits by -
-        $text = preg_replace('~[^\pL\d.]+~u', $divider, $text);
-
-        // trim
-        $text = trim($text, $divider);
-
-        // remove unwanted characters
-        $text = preg_replace('~[^-\w.]+~', '', $text);
+        $slugify = new Slugify(["separator" => "_"]);
 
-        return strtolower($text);
+        return $slugify->slugify($text);
     }
 
     // https://stackoverflow.com/a/33546903